The Performance of Post-Fall Detection Using the Cross-Dataset: Feature Vectors, Classifiers and Processing Conditions
Open Access
- 6 July 2021
- Vol. 21 (14), 4638
- https://doi.org/10.3390/s21144638
Abstract
In this study, algorithms to detect post-falls were evaluated using the cross-dataset according to feature vectors (time-series and discrete data), classifiers (ANN and SVM), and four different processing conditions (normalization, equalization, increase in the number of training data, and additional training with external data). Three-axis acceleration and angular velocity data were obtained from 30 healthy male subjects by attaching an IMU to the middle of the left and right anterior superior iliac spines (ASIS). Internal and external tests were performed using our lab dataset and SisFall public dataset, respectively. The results showed that ANN and SVM were suitable for the time-series and discrete data, respectively. The classification performance generally decreased, and thus, specific feature vectors from the raw data were necessary when untrained motions were tested using a public dataset. Normalization made SVM and ANN more and less effective, respectively. Equalization increased the sensitivity, even though it did not improve the overall performance. The increase in the number of training data also improved the classification performance. Machine learning was vulnerable to untrained motions, and data of various movements were needed for the training.Keywords
Funding Information
- Ministry of Science and ICT, South Korea (2018R1D1A1B07048575)
- Minstry of Trade, Industry and Energy, South Korea (20006386)
This publication has 31 references indexed in Scilit:
- Detecting Falls with Wearable Sensors Using Machine Learning TechniquesSensors, 2014
- An Efficient and Robust Fall Detection System Using Wireless Gait Analysis Sensor with Artificial Neural Network (ANN) and Support Vector Machine (SVM) AlgorithmsOpen Journal of Applied Biosensor, 2014
- Evaluation of waist-mounted tri-axial accelerometer based fall-detection algorithms during scripted and continuous unscripted activitiesJournal of Biomechanics, 2010
- Comparison of low-complexity fall detection algorithms for body attached accelerometersGait & Posture, 2008
- Fear of falling: measurement strategy, prevalence, risk factors and consequences among older personsAge and Ageing, 2008
- Evaluation of a threshold-based tri-axial accelerometer fall detection algorithmGait & Posture, 2007
- Falls in older people: epidemiology, risk factors and strategies for preventionAge and Ageing, 2006
- Low bone mineral density measurements in care home residents—a treatable cause of fracturesAge and Ageing, 2006
- Heterogeneous Uncertainty Sampling for Supervised LearningPublished by Elsevier BV ,1994
- PROSPECTIVE STUDY OF RESTRICTION OF ACITIVTY IN OLD PEOPLE AFTER FALLSAge and Ageing, 1987